* fhandler.h (class dev_console): Constify charset parameter of

	str_to_con.
	* fhandler_console.cc (dev_console::con_to_str): Simplify.  Always
	default to the current internal locale.
	(dev_console::get_console_cp): Always use codepage 437 for alternate
	charset.
	(dev_console::str_to_con): Constify charset parameter.
	(fhandler_console::write_normal): Always use codepage 437 for alternate
	charset.  Otherwise always default to the current internal locale.
	Replace ASCII SO with ASCII CAN.
	* strfuncs.cc: Tweka comments according to below changes.
	(sys_cp_wcstombs): Constify charset parameter.  Convert all wchar_t
	values in the Unicode private use area U+F0xx to the singlebyte
	counterpart.  Drop special handling creating ASCII SO sequence from
	U+DCxx value.  Rearrange for performance.  Replace ASCII SO with
	ASCII CAN.
	(sys_cp_mbstowcs): Constify charset parameter.  Replace ASCII SO with
	ASCII CAN.  Drop special case for U+DCxx ASCII SO sequences.  Always
	create a replacement from the Unicode private use area U+F0xx for
	invalid byte values in a multibyte sequence.  Do the same for wchar_t
	values from the U+F0xx range to make them roundtrip safe.
	* wchar.h (sys_cp_wcstombs): Constify charset parameter.
	(sys_cp_mbstowcs): Ditto.

1 files changed, 16 insertions, 13 deletions

diff --git a/winsup/cygwin/fhandler_console.cc b/winsup/cygwin/fhandler_console.cc
index 53da269c4..251a8279a 100644
--- a/winsup/cygwin/fhandler_console.cc
+++ b/winsup/cygwin/fhandler_console.cc
@@ -127,19 +127,19 @@ tty_list::get_tty (int n)
 inline DWORD
 dev_console::con_to_str (char *d, int dlen, WCHAR w)
 {
-  return sys_cp_wcstombs (*cygheap->locale.charset == 'A'
-			  ? __ascii_wctomb : cygheap->locale.wctomb,
-			  cygheap->locale.charset, d, dlen, &w, 1);
+  return sys_cp_wcstombs (cygheap->locale.wctomb, cygheap->locale.charset,
+			  d, dlen, &w, 1);
 }
 
 inline UINT
 dev_console::get_console_cp ()
 {
-  return alternate_charset_active ? GetConsoleOutputCP () : 0;
+  /* The alternate charset is always 437, just as in the Linux console. */
+  return alternate_charset_active ? 437 : 0;
 }
 
 inline DWORD
-dev_console::str_to_con (mbtowc_p f_mbtowc, char *charset,
+dev_console::str_to_con (mbtowc_p f_mbtowc, const char *charset,
 			 PWCHAR d, const char *s, DWORD sz)
 {
   return sys_cp_mbstowcs (f_mbtowc, charset, d, CONVERT_LIMIT, s, sz);
@@ -1454,16 +1454,19 @@ fhandler_console::write_normal (const unsigned char *src,
   size_t ret;
   mbstate_t ps;
   UINT cp = dev_state->get_console_cp ();
-  char charsetbuf[ENCODING_LEN + 1];
-  char *charset;
+  const char *charset;
   mbtowc_p f_mbtowc;
 
   if (cp)
-    f_mbtowc = __set_charset_from_codepage (cp, charset = charsetbuf);
+    {
+      /* The alternate charset is always 437, just as in the Linux console. */
+      f_mbtowc = __cp_mbtowc;
+      charset = "CP437";
+    }
   else
     {
+      f_mbtowc = cygheap->locale.mbtowc;
       charset = cygheap->locale.charset;
-      f_mbtowc = (*charset == 'A') ? __ascii_mbtowc : cygheap->locale.mbtowc;
     }
 
   /* First check if we have cached lead bytes of a former try to write
@@ -1606,10 +1609,10 @@ fhandler_console::write_normal (const unsigned char *src,
 	  cursor_set (false, 0, y);
 	  break;
 	case ERR:
-	  /* Don't print chars marked as ERR chars, except for a SO sequence
-	     which is printed as singlebyte chars from the UTF Basic Latin
-	     and Latin 1 Supplement plains. */
-	  if (*found == 0x0e)
+	  /* Don't print chars marked as ERR chars, except for a ASCII CAN
+	     sequence which is printed as singlebyte chars from the UTF
+	     Basic Latin and Latin 1 Supplement plains. */
+	  if (*found == 0x18)
 	    {
 	      write_replacement_char ();
 	      if (found + 1 < end)